/**
* oom_badness - calculate a numeric value for how bad this task has been
* @p: task struct of which task we should calculate
+ * @p: current uptime in seconds
*
* The formula used is relatively simple and documented inline in the
* function. The main rationale is that we want to select a good task
* of least surprise ... (be careful when you change it)
*/
-static int badness(struct task_struct *p)
+unsigned long badness(struct task_struct *p, unsigned long uptime)
{
- int points, cpu_time, run_time, s;
+ unsigned long points, cpu_time, run_time, s;
+ struct list_head *tsk;
if (!p->mm)
return 0;
- if (p->flags & PF_MEMDIE)
- return 0;
/*
* The memory size of the process is the basis for the badness.
*/
points = p->mm->total_vm;
- /* add vserver badness ;) */
+ /* FIXME add vserver badness ;) */
+
+ /*
+ * Processes which fork a lot of child processes are likely
+ * a good choice. We add the vmsize of the childs if they
+ * have an own mm. This prevents forking servers to flood the
+ * machine with an endless amount of childs
+ */
+ list_for_each(tsk, &p->children) {
+ struct task_struct *chld;
+ chld = list_entry(tsk, struct task_struct, sibling);
+ if (chld->mm != p->mm && chld->mm)
+ points += chld->mm->total_vm;
+ }
/*
- * CPU time is in seconds and run time is in minutes. There is no
- * particular reason for this other than that it turned out to work
- * very well in practice.
+ * CPU time is in tens of seconds and run time is in thousands
+ * of seconds. There is no particular reason for this other than
+ * that it turned out to work very well in practice.
*/
- cpu_time = (p->utime + p->stime) >> (SHIFT_HZ + 3);
- run_time = (get_jiffies_64() - p->start_time) >> (SHIFT_HZ + 10);
+ cpu_time = (cputime_to_jiffies(p->utime) + cputime_to_jiffies(p->stime))
+ >> (SHIFT_HZ + 3);
+
+ if (uptime >= p->start_time.tv_sec)
+ run_time = (uptime - p->start_time.tv_sec) >> 10;
+ else
+ run_time = 0;
s = int_sqrt(cpu_time);
if (s)
*/
if (cap_t(p->cap_effective) & CAP_TO_MASK(CAP_SYS_RAWIO))
points /= 4;
+
+ /*
+ * Adjust the score by oomkilladj.
+ */
+ if (p->oomkilladj) {
+ if (p->oomkilladj > 0)
+ points <<= p->oomkilladj;
+ else
+ points >>= -(p->oomkilladj);
+ }
+
#ifdef DEBUG
printk(KERN_DEBUG "OOMkill: task %d (%s) got %d points\n",
p->pid, p->comm, points);
*/
static struct task_struct * select_bad_process(void)
{
- int maxpoints = 0;
+ unsigned long maxpoints = 0;
struct task_struct *g, *p;
struct task_struct *chosen = NULL;
+ struct timespec uptime;
+ do_posix_clock_monotonic_gettime(&uptime);
do_each_thread(g, p)
- if (p->pid) {
- int points = badness(p);
- if (points > maxpoints) {
+ /* skip the init task with pid == 1 */
+ if (p->pid > 1) {
+ unsigned long points;
+
+ /*
+ * This is in the process of releasing memory so wait it
+ * to finish before killing some other task by mistake.
+ */
+ if ((unlikely(test_tsk_thread_flag(p, TIF_MEMDIE)) || (p->flags & PF_EXITING)) &&
+ !(p->flags & PF_DEAD))
+ return ERR_PTR(-1UL);
+ if (p->flags & PF_SWAPOFF)
+ return p;
+
+ points = badness(p, uptime.tv_sec);
+ if (points > maxpoints || !chosen) {
chosen = p;
maxpoints = points;
}
- if (p->flags & PF_SWAPOFF)
- return p;
}
while_each_thread(g, p);
return chosen;
*/
static void __oom_kill_task(task_t *p)
{
+ if (p->pid == 1) {
+ WARN_ON(1);
+ printk(KERN_WARNING "tried to kill init!\n");
+ return;
+ }
+
task_lock(p);
if (!p->mm || p->mm == &init_mm) {
WARN_ON(1);
* exit() and clear out its resources quickly...
*/
p->time_slice = HZ;
- p->flags |= PF_MEMALLOC | PF_MEMDIE;
+ set_tsk_thread_flag(p, TIF_MEMDIE);
- /* This process has hardware access, be more careful. */
- if (cap_t(p->cap_effective) & CAP_TO_MASK(CAP_SYS_RAWIO)) {
- force_sig(SIGTERM, p);
- } else {
- force_sig(SIGKILL, p);
- }
+ force_sig(SIGKILL, p);
}
static struct mm_struct *oom_kill_task(task_t *p)
{
struct mm_struct *mm = get_task_mm(p);
- if (!mm || mm == &init_mm)
+ task_t * g, * q;
+
+ if (!mm)
+ return NULL;
+ if (mm == &init_mm) {
+ mmput(mm);
return NULL;
+ }
+
__oom_kill_task(p);
+ /*
+ * kill all processes that share the ->mm (i.e. all threads),
+ * but are in a different thread group
+ */
+ do_each_thread(g, q)
+ if (q->mm == mm && q->tgid != p->tgid)
+ __oom_kill_task(q);
+ while_each_thread(g, q);
+
return mm;
}
+static struct mm_struct *oom_kill_process(struct task_struct *p)
+{
+ struct mm_struct *mm;
+ struct task_struct *c;
+ struct list_head *tsk;
+
+ /* Try to kill a child first */
+ list_for_each(tsk, &p->children) {
+ c = list_entry(tsk, struct task_struct, sibling);
+ if (c->mm == p->mm)
+ continue;
+ mm = oom_kill_task(c);
+ if (mm)
+ return mm;
+ }
+ return oom_kill_task(p);
+}
/**
* oom_kill - kill the "best" process when we run out of memory
* OR try to be smart about which process to kill. Note that we
* don't have to be perfect here, we just have to be good.
*/
-static void oom_kill(void)
+void out_of_memory(int gfp_mask)
{
- struct mm_struct *mm;
- struct task_struct *g, *p, *q;
-
+ struct mm_struct *mm = NULL;
+ task_t * p;
+
read_lock(&tasklist_lock);
retry:
p = select_bad_process();
+ if (PTR_ERR(p) == -1UL)
+ goto out;
+
/* Found nothing?!?! Either we hang forever, or we panic. */
if (!p) {
+ read_unlock(&tasklist_lock);
show_free_areas();
panic("Out of memory and no killable processes...\n");
}
- mm = oom_kill_task(p);
+ printk("oom-killer: gfp_mask=0x%x\n", gfp_mask);
+ show_free_areas();
+ mm = oom_kill_process(p);
if (!mm)
goto retry;
- /*
- * kill all processes that share the ->mm (i.e. all threads),
- * but are in a different thread group
- */
- do_each_thread(g, q)
- if (q->mm == mm && q->tgid != p->tgid)
- __oom_kill_task(q);
- while_each_thread(g, q);
- if (!p->mm)
- printk(KERN_INFO "Fixed up OOM kill of mm-less task\n");
- read_unlock(&tasklist_lock);
- mmput(mm);
- /*
- * Make kswapd go out of the way, so "p" has a good chance of
- * killing itself before someone else gets the chance to ask
- * for more memory.
- */
- yield();
- return;
-}
-
-/**
- * out_of_memory - is the system out of memory?
- */
-void out_of_memory(void)
-{
- /*
- * oom_lock protects out_of_memory()'s static variables.
- * It's a global lock; this is not performance-critical.
- */
- static spinlock_t oom_lock = SPIN_LOCK_UNLOCKED;
- static unsigned long first, last, count, lastkill;
- unsigned long now, since;
-
- /*
- * Enough swap space left? Not OOM.
- */
- if (nr_swap_pages > 0)
- return;
-
- spin_lock(&oom_lock);
- now = jiffies;
- since = now - last;
- last = now;
-
- /*
- * If it's been a long time since last failure,
- * we're not oom.
- */
- last = now;
- if (since > 5*HZ)
- goto reset;
-
- /*
- * If we haven't tried for at least one second,
- * we're not really oom.
- */
- since = now - first;
- if (since < HZ)
- goto out_unlock;
-
- /*
- * If we have gotten only a few failures,
- * we're not really oom.
- */
- if (++count < 10)
- goto out_unlock;
-
- /*
- * If we just killed a process, wait a while
- * to give that task a chance to exit. This
- * avoids killing multiple processes needlessly.
- */
- since = now - lastkill;
- if (since < HZ*5)
- goto out_unlock;
-
- /*
- * Ok, really out of memory. Kill something.
- */
- lastkill = now;
-
- /* oom_kill() sleeps */
- spin_unlock(&oom_lock);
- oom_kill();
- spin_lock(&oom_lock);
+ out:
+ read_unlock(&tasklist_lock);
+ if (mm)
+ mmput(mm);
-reset:
/*
- * We dropped the lock above, so check to be sure the variable
- * first only ever increases to prevent false OOM's.
+ * Give "p" a good chance of killing itself before we
+ * retry to allocate memory.
*/
- if (time_after(now, first))
- first = now;
- count = 0;
-
-out_unlock:
- spin_unlock(&oom_lock);
+ __set_current_state(TASK_INTERRUPTIBLE);
+ schedule_timeout(1);
}